8. What does the centroid in k-means represent?

The mean of all points in a cluster

10. If two clusters overlap significantly, what issue might k-means face?

It may assign points incorrectly between the two clusters

2. What is the primary goal of k-means clustering?

To partition data into k groups based on similarity

14. What is the main difference between k-means and hierarchical clustering?

K-means requires pre-selecting k

13. Which of the following is NOT a common use case of k-means clustering?

Predicting stock prices based on historical data

9. How does k-means decide which cluster a data point belongs to?

By assigning it to the nearest centroid based on distance

7. Which of the following is NOT a step in the k-means algorithm?

Assign class labels to clusters

5. What happens if you set k too high in k-means clustering?

Overfitting - clusters may become too small and meaningless

12. What happens if two clusters have very different sizes in k-means?

The smaller cluster may get absorbed into the larger one

3. What is the "elbow method" used for in k-means?

Determining the optimal number of clusters

6. How does k-means clustering handle outliers?

Poorly - outliers can pull centroids away from actual clusters

4. What does the Euclidean distance measure in k-means clustering?

The straight line distance between a data point and a centroid

studbud

K-Means Clustering: What, Why, and How

15 termsStudBud Administration15 plays

Imported from external platform

Flashcards15 cardsFPractice quizPHost liveL

Questions 15

Answers

1
8. What does the centroid in k-means represent?
The data point closest to the center of a cluster
A randomly selected point from the dataset
The mean of all points in a cluster
The point with the highest variance in a cluster
2
11. K-means is meant for categorical data
True
False
3
10. If two clusters overlap significantly, what issue might k-means face?
It will fail and return an error
It may assign points incorrectly between the two clusters
It will always merge them into a single cluster
It will create new clusters to separate them
4
2. What is the primary goal of k-means clustering?
To partition data into k groups based on similarity
To predict continuous numerical values
To reduce dimensionality
To classify data using labeled training examples
5
I feel more confident about my k-means knowledge now!
True
False
6
14. What is the main difference between k-means and hierarchical clustering?
K-means is more computationally expensive
Hierarchical clustering always performs better than k-means
Hierarchical clustering only works for small data sets
K-means requires pre-selecting k
7
What type of learning is k-means clustering?
Supervised Learning
Unsupervised Learning
Semi-Supervised Learning
Reinforcement Learning
8
13. Which of the following is NOT a common use case of k-means clustering?
Anomaly detection in cybersecurity
Predicting stock prices based on historical data
Customer segmentation in marketing
Image compression and color quantization
9
9. How does k-means decide which cluster a data point belongs to?
By assigning it to the nearest centroid based on distance
By looking at neighboring clusters
By randomly assigning points to clusters
By checking if the point was the same cluster in the previous iteration
10
7. Which of the following is NOT a step in the k-means algorithm?
Recalculate cluster centroids
Assign points to the closest centroid
Assign class labels to clusters
Select k initial centroids
11
5. What happens if you set k too high in k-means clustering?
No effect - k-means always finds the best clustering
Underfitting - clusters become too broad
Overfitting - clusters may become too small and meaningless
The centroids will merge over time
12
12. What happens if two clusters have very different sizes in k-means?
It creates a new cluster to fix the imbalance
The smaller cluster may get absorbed into the larger one
The algorithm struggles to work, and may stop running
K-means automatically balances the cluster sizes
13
3. What is the "elbow method" used for in k-means?
Determining the optimal number of clusters
Measuring the performance of k-means
Handling outliers in the data
Selecting initial centroids
14
6. How does k-means clustering handle outliers?
Poorly - outliers can pull centroids away from actual clusters
It assigns them to their own cluster
It automatically removes them
It ignores them completely
15
4. What does the Euclidean distance measure in k-means clustering?
The average of all data points in a cluster
The number of data points in a cluster
The straight line distance between a data point and a centroid
The density of a cluster

K-Means Clustering: What, Why, and How Flashcards | StudBud